{"kind":"task","effective_mode":"full","benchmark":{"kind":"benchmark","effective_mode":"full","slug":"mmlu-pro","formal_name":"MMLU-Pro","introduction":"MMLU-Pro rebuilds MMLU with ten answer options instead of four and removes items that no longer separate models. Questions span fourteen academic and professional subjects.","introduction_ja":"","introduction_en":"","category":"Category not supplied","task_count":null,"acquisition_status":"Acquisition status not supplied","official_url":"https://huggingface.co/datasets/TIGER-Lab/MMLU-Pro","indexing_mode":"index","profile":{"resources":[],"task_format":"","scoring":"","metric":"","size":"","answer_access":"","license":"","citation":"","maintainer":"","released":"","why_hard":"","related":[],"history":"","construction":"","limitations":"","saturation":"","scores":[]}},"task_id":"3233a2a5-957c-5974-8025-5a209b0b3807","task_key":"default--test--1575","task_revision_id":"1","upstream_id":"1575","short_description":"Which one of the following statements is false?","config":"default","split":"test","body":"{\"category\":\"law\",\"options\":\"['Protocol 14 changed the committee that hears admissibility cases from a three judge to a one judge formation', 'Protocol 14 added a new criterion for admissibility', 'Protocol 14 abolished the Commission of Human Rights', 'Protocol 14 extended the judicial term of office for the European Court of Human Rights']\",\"question\":\"Which one of the following statements is false?\",\"src\":\"ori_mmlu-international_law\"}","display_format":"text","language":"","answer_status":"published","assets":[],"source_url":"https://huggingface.co/datasets/TIGER-Lab/MMLU-Pro","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}